CN111260525A - Community security situation perception and early warning method, system and storage medium - Google Patents
Community security situation perception and early warning method, system and storage medium Download PDFInfo
- Publication number
- CN111260525A CN111260525A CN202010047997.1A CN202010047997A CN111260525A CN 111260525 A CN111260525 A CN 111260525A CN 202010047997 A CN202010047997 A CN 202010047997A CN 111260525 A CN111260525 A CN 111260525A
- Authority
- CN
- China
- Prior art keywords
- data
- community
- behavior
- early warning
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000008447 perception Effects 0.000 title abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 84
- 238000012545 processing Methods 0.000 claims abstract description 59
- 238000001514 detection method Methods 0.000 claims abstract description 43
- 230000004927 fusion Effects 0.000 claims abstract description 22
- 230000006399 behavior Effects 0.000 claims description 140
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 22
- 238000005516 engineering process Methods 0.000 claims description 17
- 238000012847 principal component analysis method Methods 0.000 claims description 8
- 238000013499 data model Methods 0.000 claims description 4
- 238000012880 independent component analysis Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 12
- 238000007726 management method Methods 0.000 description 17
- 238000013507 mapping Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 12
- 238000013467 fragmentation Methods 0.000 description 11
- 238000006062 fragmentation reaction Methods 0.000 description 11
- 230000007246 mechanism Effects 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 10
- 238000012544 monitoring process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 241000282414 Homo sapiens Species 0.000 description 5
- 230000008901 benefit Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 5
- 230000003068 static effect Effects 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 239000012634 fragment Substances 0.000 description 4
- 239000000779 smoke Substances 0.000 description 4
- 230000000739 chaotic effect Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000005021 gait Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012097 association analysis method Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a community security situation perception and early warning method, a community security situation perception and early warning system and a storage medium, wherein the method comprises the following steps: acquiring current community data detected by a multi-source heterogeneous sensor; inputting the current community data into a pre-established behavior detection model based on dynamic network time-space, performing data feature fusion, and extracting behavior feature data; sending the behavior characteristic data to a central analysis platform for processing and analysis; and sensing and early warning the community security situation according to the processing and analyzing results fed back by the central analysis platform. Compared with the prior art, the invention realizes real-time situation perception and early warning and avoids false alarm in community activities.
Description
Technical Field
The invention relates to the technical field of intelligent communities, in particular to a community security situation perception and early warning method and system based on a dynamic network spatio-temporal model and a storage medium.
Background
The intelligent community is a mode for integrating various existing service resources of the community by using various intelligent technologies and modes and providing multiple convenient services such as government affairs, commerce, entertainment, education, medical care, life mutual assistance and the like for the community. From the application direction, the intelligent community can improve the transaction efficiency by intelligent government affairs, improve the life of people by intelligent people, build intelligent life by intelligent families, and improve the community quality by intelligent communities.
The smart city (community) is a new concept of community management and a new mode of social management innovation in new situation. The method has the advantages that the Internet and the Internet of things are fully utilized, the method relates to the fields of intelligent buildings, intelligent home, road network monitoring, personal health, digital life and the like, and the advantages of developed Information and Communication Technology (ICT) industry, excellent telecommunication service and information-based infrastructure and the like are fully exerted.
The Chinese patent document with the application number of CN 107659645A and the name of the integrated intelligent community system based on the Internet of things comprises a property application layer, a data transmission layer and a service management layer, combines data acquisition, video monitoring, automatic alarm and intelligent identification, and performs networking control and processing on community potential safety hazard information, resource utilization and community service in a unified manner. The system performs detailed operation of deployment of the Internet of things for communities, but the management method of data is still more traditional, the calculation is not efficient, and the accurate feedback of complex abnormal behaviors (aiming at people) cannot be performed.
The Chinese patent document with the application number of CN 106713481A and the name of the intelligent community security system based on the Internet of things comprises an access control system, a video screen monitoring system, a property management subsystem and a server subsystem, wherein video image information and IC card information are associated, and inquiry and monitoring of various equipment events are realized through a management server, so that the intelligent access control and the community monitoring are combined. This method uses a large amount of resources on the hardware and can also achieve certain effects, but is not efficient.
The current smart community has the following problems:
1. the existing safety situation perception and early warning system is not comprehensive in design field, and the data of the sensor based on the safety situation perception and early warning system is single.
2. The comprehensive analysis can not be carried out by integrally fusing various data of the multi-source heterogeneous sensor, and only the early warning is realized by simply analyzing the original data.
3. Data supporting spatio-temporal feature query required by continuous behavior analysis cannot be effectively managed, and data storage and query efficiency is low, so that real prevention cannot be achieved.
4. The community can not be fused online and offline, so that false early warning can be caused sometimes.
5. The failure to optimize the central and data source computing power results in significant waste of computing resources in data computing.
Disclosure of Invention
The invention mainly aims to provide a community security situation awareness and early warning method, a community security situation awareness and early warning system and a storage medium based on a dynamic network space-time model, and aims to realize the purposes that on the basis of deploying a multisource heterogeneous Internet of things in a community, the time-space characteristics of data are fused for continuous behavior analysis, online and offline data are fused for security monitoring and event early warning, edge calculation and high-performance calculation technologies are used for efficiently managing the data, and real-time situation awareness and early warning are realized.
In order to achieve the above purpose, the present invention provides a community security situation perception and early warning method, including:
acquiring current community data detected by a multi-source heterogeneous sensor;
inputting the current community data into a pre-established behavior detection model based on dynamic network time-space, performing data feature fusion, and extracting behavior feature data;
sending the behavior characteristic data to a central analysis platform for processing and analysis;
and sensing and early warning the community security situation according to the processing and analyzing results fed back by the central analysis platform.
The further technical scheme of the invention is that the step of sending the behavior characteristic data to a central analysis platform for processing and analysis comprises the following steps:
and sending the behavior characteristic data to a central analysis platform, and processing and analyzing the behavior characteristic data by the central analysis platform by adopting a high-pass data processing and high-performance real-time computing engine.
The further technical scheme of the invention is that the step of inputting the current community data into a pre-established behavior detection model based on dynamic network space-time to perform data feature fusion and extracting the behavior feature data comprises the following steps:
and inputting the current community data into a pre-established behavior detection model based on dynamic network space-time to perform data feature fusion, and extracting behavior feature data by adopting a principal component analysis method, a linear discriminant analysis method, a multidimensional scale analysis method, an analysis method based on flow learning, an independent component analysis method or a kernel principal component analysis method.
The further technical scheme of the invention is that the step of obtaining the current community data detected by the multi-source heterogeneous sensor further comprises the following steps:
processing the current community data by adopting a multilayer and data processing and computing system based on an edge computing technology to obtain processed community data;
the step of inputting the current community data into a pre-established dynamic network spatio-temporal based behavior detection model comprises the following steps:
and inputting the processed community data into a pre-established behavior detection model based on dynamic network space-time.
The further technical scheme of the invention is that the step of obtaining the current community data detected by the multi-source heterogeneous sensor comprises the following steps:
a behavior detection model based on dynamic network space-time is established in advance;
the behavior detection model based on the dynamic network space-time is an abstract data model which is established aiming at a network space and takes continuous behaviors as objects;
the step of establishing a dynamic network spatiotemporal behavior detection model comprises the following steps:
based on interesting continuous behaviors, a time-space feature structure capable of fusing multi-source heterogeneous sensor data is established, and meanwhile, adjustable weights of different time-space feature dimensions are determined according to the obvious feature dimensions of specific access data.
The further technical scheme of the invention is that the step of pre-establishing the behavior detection model based on the dynamic network space-time comprises the following steps:
and pre-establishing a network space-time characteristic model based on continuous behaviors.
The further technical scheme of the invention is that the step of pre-establishing the behavior detection model based on the dynamic network space-time further comprises the following steps:
and pre-establishing a network space environment characteristic model based on online and offline fusion data.
The further technical scheme of the invention is that the step of pre-establishing the behavior detection model based on the dynamic network space-time further comprises the following steps:
and (4) establishing an abstract network space abnormal behavior characteristic library based on dynamic update in advance.
In order to achieve the above object, the present invention further provides a community security situation awareness and early warning system, where the system includes a memory, a processor, and a community security situation awareness and early warning program stored on the processor, and the community security situation awareness and early warning program executes the steps of the method when called by the processor.
To achieve the above object, the present invention further provides a computer-readable storage medium, where a community security situation awareness and early warning program is stored, and the community security situation awareness and early warning program executes the steps of the method when being called by a processor.
The community security situation perception and early warning method has the beneficial effects that: according to the technical scheme, the current community data detected by the multi-source heterogeneous sensor is acquired; inputting the current community data into a pre-established behavior detection model based on dynamic network time-space, performing data feature fusion, and extracting behavior feature data; sending the behavior characteristic data to a central analysis platform for processing and analysis; and carrying out community security situation perception and early warning according to the processing and analyzing results fed back by the central analysis platform, realizing real-time situation perception and early warning, and avoiding false alarm in community activities.
Drawings
FIG. 1 is a schematic flow chart diagram of a first embodiment of a community security situation awareness and early warning method based on a dynamic network spatiotemporal model according to the present invention;
FIG. 2 is a schematic flow chart of a second embodiment of the community security situation awareness and early warning method of the present invention;
FIG. 3 is a system architecture diagram of a community security posture awareness and early warning system based on a dynamic network spatiotemporal model;
FIG. 4 is a flow chart for behavioral data modeling;
FIG. 5 is a schematic diagram of a B + tree data index;
FIG. 6 is a schematic diagram of a hash shard management mechanism;
fig. 7 is a schematic diagram of edge calculation.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1 to 7, the invention provides a dynamic network spatio-temporal model-based community security situation awareness and early warning method, which is applied to a dynamic network spatio-temporal model-based community security situation awareness and early warning system as shown in fig. 3.
Specifically, referring to fig. 1, fig. 1 is a schematic flow chart of a first embodiment of a community security situation awareness and early warning method based on a dynamic network spatio-temporal model according to the present invention.
As shown in fig. 1, in this embodiment, the community security situation awareness and early warning method based on the dynamic network spatio-temporal model includes the following steps:
and step S10, current community data detected by the multi-source heterogeneous sensor is obtained.
As a scene with large human activities, the community has rich multi-source heterogeneous sensor types, including but not limited to camera sensors, card readers, fingerprint readers, temperature sensors, smoke sensors, infrared sensors and other functional sensors.
And step S20, inputting the current community data into a pre-established behavior detection model based on dynamic network space-time, performing data feature fusion, and extracting behavior feature data.
In the embodiment, various behaviors contained in the community sensor data are considered, so that the embodiment not only considers the timeliness of a series of behaviors when establishing a behavior detection model, but also considers the spatial characteristics of behavior occurrence, the network space environment of online and offline fusion data, and the dynamically updated abstract network space abnormal behavior so as to avoid the occurrence of false early warning.
It can be understood that, due to the abundance of sensors and the arrival of the internet of things era of the internet of everything interconnection, the number of local sensors such as communities is increased, data generated by edge devices is also increased rapidly, higher data transmission bandwidth and requirements are brought, meanwhile, the security situation perception model also provides higher real-time requirements for data processing, and the traditional cloud computing model cannot efficiently solve the dilemma.
In this embodiment, after the current community data is processed by using a multi-layer and data processing and computing system based on an edge computing technology to obtain processed community data, the processed community data is input to a pre-established behavior detection model based on a dynamic network space-time, data feature fusion is performed, and behavior feature data is extracted.
In this embodiment, after the processed community data is input to a pre-established behavior detection model based on dynamic network space-time and data feature fusion, the behavior feature data may be extracted by a principal component analysis method, a linear discriminant analysis method, a multidimensional scale analysis method, an analysis method based on stream learning, an independent component analysis method, or a kernel principal component analysis method.
And step S30, sending the behavior characteristic data to a central analysis platform for processing and analysis.
And after the behavior characteristic data are sent to a central analysis platform, the central analysis platform carries out parallel operation on the behavior characteristic data, processes and analyzes the behavior characteristic data, and monitors and discovers whether abnormal behaviors exist in the community or not according to processing and analyzing results.
In this embodiment, after the behavior feature data is sent to the central analysis platform, the central analysis platform may use a high-pass data processing and high-performance real-time computing engine to process and analyze the behavior feature data,
and step S40, carrying out community security situation perception and early warning according to the processing and analysis results fed back by the central analysis platform.
After receiving the processing and analysis results fed back by the central analysis platform, community security situation perception and early warning are carried out according to the processing and analysis results fed back by the central analysis platform, and therefore real-time situation perception and early warning are truly achieved.
According to the technical scheme, the current community data detected by the multi-source heterogeneous sensor is obtained; inputting the current community data into a pre-established behavior detection model based on dynamic network time-space, performing data feature fusion, and extracting behavior feature data; sending the behavior characteristic data to a central analysis platform for processing and analysis; and carrying out community security situation perception and early warning according to the processing and analyzing results fed back by the central analysis platform, realizing real-time situation perception and early warning, and avoiding false alarm in community activities.
Referring to fig. 2, fig. 2 is a schematic flow chart of a second embodiment of the community security situation awareness and early warning method of the present invention.
The present embodiment is different from the first embodiment shown in fig. 1in that, in step S10, the step of acquiring current community data detected by the multi-source heterogeneous sensor includes:
step S00, pre-establishing a dynamic network space-time based behavior detection model, wherein the dynamic network space-time based behavior detection model is an abstract data model which is established aiming at a network space and takes continuous behaviors as objects;
the step of establishing a dynamic network spatiotemporal behavior detection model comprises the following steps:
based on interesting continuous behaviors, a time-space feature structure capable of fusing multi-source heterogeneous sensor data is established, and meanwhile, adjustable weights of different time-space feature dimensions are determined according to the obvious feature dimensions of specific access data.
As an embodiment, the step of pre-establishing the dynamic network spatio-temporal based behavior detection model includes: and pre-establishing a network space-time characteristic model based on continuous behaviors.
In the embodiment, after the current community data detected by the multi-source heterogeneous sensor is acquired, the behavior can be depicted to a certain extent, but if a complex event needs to be processed, the continuous behavior needs to be analyzed according to the characteristics, and the analysis of the continuous behavior needs a network space spatiotemporal characteristic model of the continuous behavior.
As an embodiment, the step of pre-establishing the dynamic network spatio-temporal based behavior detection model further includes: and pre-establishing a network space-time characteristic model based on continuous behaviors.
In the embodiment, it is considered that data generated by a part of sensors is picture information with a certain number of frames per second, and all the pictures contain community behavior information in time and space dimensions, but various activities occur in real time in the environment of a community, so that a network space environment feature model based on online and offline fusion data needs to be established by adopting a method of extracting the features of the online and offline data and fusing the extracted features with the online data.
As an embodiment, the step of pre-establishing the dynamic network spatio-temporal based behavior detection model further includes: and (4) establishing an abstract network space abnormal behavior characteristic library based on dynamic update in advance.
In the embodiment, the feature library is updated on the character event, and the feature library of the abnormal behavior is updated in space, that is, the environment where the abnormal behavior is located is dynamically updated, so that real-time community security situation perception and early warning are realized.
The community security situation awareness and early warning method of the present invention is described in detail below with reference to fig. 1 to 7 by way of example.
The invention provides a community security situation perception and early warning method based on a dynamic network time-space model.
The specific processing flow of the community security situation perception and early warning method is as follows:
1. feature mapping based on multi-source heterogeneous sensing data to abstract network space
The first step of the community security situation perception and early warning system model is element extraction of community security situations, and the purpose of feature mapping from multisource heterogeneous sensing data to an abstract network space is achieved. The data in the original target (sensor) field can be used by the target field (community security situation perception and early warning system).
The community is used as a scene with large people activities, and the types of the multi-source heterogeneous sensors are very rich, wherein the multi-source heterogeneous sensors include but are not limited to camera sensors, card readers, fingerprint readers, temperature sensors, smoke sensors, infrared sensors and other functional sensors.
The overall, real-time and dynamic security situation perception of a distributed network is realized by deploying a multi-source heterogeneous sensor, the primary thing is to process a data source, wherein the data source is direct data obtained by the multi-source heterogeneous sensor, and if the original data obtained by the sensor is directly used, the problems of unobvious characteristics, dimension explosion and the like can be caused, so that data analysis is influenced, and the data belongs to bottom-layer low-level data. The data itself is not difficult to observe and process, but the data is not directly needed and available by the community security situation perception and early warning system, so a series of processing needs to be carried out on the data. This processing is primarily a feature mapping of the data into an abstract network space. Dimension reduction is a mainstream means of feature mapping from data to abstract network space, and different methods can be adopted according to the difference of the quantity, quality and dimension of data.
Before the data is subjected to feature mapping, data cleaning needs to be carried out on the sensing data, for example, missing value processing is carried out, due to the characteristics of large density and wide distribution, data missing is easily formed on the distribution of the time stamps of the community sensor, and according to the importance of the data missing, methods such as data removing, data filling, data resampling and the like are respectively adopted.
There are many methods for feature mapping, i.e. extracting features, such as principal component analysis, where original n-dimensional data is mapped to k-dimension, which is a completely new orthogonal principal component feature. The method is simple in concept and convenient to calculate, but has no uniform standard for determining the principal components and the quantity thereof. And a linear discriminant analysis method can be adopted to project the high-dimensional data sample to the best discriminant vector space, so that the sample data has the best separable type in the space. Moreover, a multi-dimensional analysis method can be adopted, and a representation of the samples is generated in a low-dimensional space according to the distance relation or dissimilarity relation between the samples, so that the method can effectively and visually observe the intrinsic relation of the data. Further, a method based on flow learning, an independent component analysis method, a kernel principal component analysis method, and the like can be used.
For example, pedestrians in communities all have various attributes, sex, height, thickness, dressing, whether the pedestrians are capped or not and whether the pedestrians wear glasses or not, and according to different problems, the required components are different, so that the principal component analysis method is selected to reduce the dimension of the pedestrians and make feature mapping.
Feature mapping of multi-source sensing data is an important part, and original data can be selected for subsequent features and analyzed, diagnosed, predicted and the like only after efficient data cleaning and feature mapping, and the feature mapping is also the first work for completing a set of community security situation perception and early warning system.
With pedestrian a entering a cell, data in both the time and space dimensions, i.e. data generated over a period of time in a certain environment, a map is generated like the following:
{[Id:2019.12.15-00001],[sex:male],[glasses:1],[hat:0],[gait:run]{[2019.12.15|24:05:Gate]；[2019.12.15|24:09:building1],[2019.12.15|11:20:building4],[2019.12.15|24:20:building18]}}。
the method respectively shows that a man wearing glasses runs into a cell gate and is shot by a camera to enter 1,4 and 18 buildings respectively, the stay time of each building is not long, namely a text expression generated by mapping original data of a multi-source heterogeneous sensor is generated, but not every kind of data is important and necessary when data processing is carried out, certain principal component analysis is needed, the time of the principal component of the man staying in each building is extracted, gait analysis is running instead of normal walking, therefore, feedback is made in a background, and early warning is given out when the man acts abnormally.
2. Network space spatio-temporal feature models for continuous behavior:
after the sensor features are extracted, certain characterizations can be made of the behavior. But if complex events are to be processed, continuous behavior needs to be analyzed in terms of features. Analyzing the continuous behavior requires a model of the spatiotemporal characteristics of the network space of the continuous behavior. Therefore, a feature representation of continuous behavior and construction of a continuous behavior (abnormal behavior) model are required. FIG. 4 shows a continuous behavior modeling flow.
Taking video sensor data as an example, the specific flow is as follows:
1) data of the sensor device is obtained and serialized.
2) Denoising the video sequence, and screening the video data, for example, selecting frames with rich characteristic behaviors and filtering the video to select the required target block.
3) The method can be carried out by selecting a 3D-SIFT method, extends the classic SIFT operator from a static graph to a dynamic video sequence, adds time t as a third dimension, and accurately captures the spatiotemporal idiosyncrasy of video data.
4) And establishing a behavior detection model, wherein the behavior detection model with multi-attribute fusion is established according to the needs of community scenes, and comprises a time domain chaotic attribute, a space domain chaotic model attribute and an optical flow attribute. The time domain confusion model is characterized in that the operation of a target local area is described from time, for example, a community enters a stranger. Spatial clutter models describe the behavior of a target spatially, such as a vehicle that suddenly rushes out of a street that is originally empty in a community and fails to recognize its license plate. The optical flow attribute refers to that all behaviors have speed and direction characteristics, the speed of normal behaviors is not too high, the direction change is not obvious, and the behavior characteristics of a target area can be fully described through a space-time chaotic attribute. And performing deep fusion on the three attributes to establish a behavior detection model.
Taking community vehicle access management as an example, a community enters a vehicle, the vehicle has no abnormality before entering the community, but the video shot by the camera is processed after entering the community, the vehicle behavior is expressed, the monitoring area which passes through a plurality of cameras at an excessively high speed is found, a behavior model of the vehicle is established, analysis and detection are carried out, and abnormal behavior is judged and early warning is carried out in time.
3. And (3) integrating the behavior record indexes of the space-time characteristics and adopting a boundary redundancy fragment management mechanism:
the community sensor data comprises various behaviors, the time characteristics of a series of behaviors are considered when continuous behaviors are modeled, and additionally, the spatial characteristics of behavior occurrence are also considered in the invention. Since there are many similarities and uncertainties in behavior characteristics, from the viewpoint of data structure, such frame-by-frame images are stored in an orderly organization, and it is desirable to search for a range of data at the time of searching, so that the indexing method adopted for data is a B + tree indexing method, and the indexing of community behavior data can be substantially represented in fig. 5.
Aiming at the search of community behaviors, starting from a root node, performing binary search on a keyword sequence in the node, if the keyword sequence is searched, finishing, and if the keyword sequence is not searched, entering a son node in a range to which the query keyword belongs; and repeating, knowing that the corresponding son pointer is a leaf node of the airspace, establishing the record index of the community behavior in such a way.
However, in a long-term environment such as community behavior data, the data is very large and is continuously updated over a certain time, so that a data fragmentation management technology is used. Data fragmentation management is to store data on different logical nodes to reduce the data operation pressure of a single node. Data fragmentation needs to carefully select a fragmentation strategy, so that the effect of data distribution as even as possible is achieved. If the data fragmentation is uneven and the data volume is large, the data fragmentation is not utilized to perform good fragmentation management on the existing data. One method to avoid hot spots is to randomly fragment the data, but the disadvantage is that a query operation needs to be performed on all fragments. Data fragmentation for the pure key-value data model is relatively simple because read and write operations all rely on a single primary key. Key hash fragmentation is chosen here in order to be able to be as uniform fragmentation as possible.
For example, as shown in fig. 6, a schematic diagram of a hash fragmentation management mechanism for data generated by a certain camera is shown.
The behavior record index and the fragment management mechanism are established according to the mode, so that the data can be more effectively stored, read and written.
4. Network space environment (context) feature model based on online-offline fusion data:
for sensing equipment such as various sensors in a community, data generated and received by some sensors only needs to be matched with rules, and the data only needs to be calculated for an offline algorithm (generally, rules), such as a temperature sensor, a humidity sensor, a smoke alarm, face recognition in community access control and the like. The situation awareness and early warning system in the relative field can be realized only by data matching. For example, a temperature sensor may be determined to be potentially in a fire when the temperature sensor is above 60 degrees celsius in a typical residential environment. However, more data in the community environment is generated by sensing equipment such as a camera or a monitor, and the data generated by such sensors is image information of a certain number of frames per second, and the images all contain community behavior information in the time and space dimensions. Although initial central algorithms such as behavior classification have been empirically trained online and can be used directly in real-time community behavior classification. But a wide variety of activities occur in real time in the context of a community. Therefore, a method for extracting the characteristics of the online data and fusing the characteristics with the online data is needed.
For example, a community resident issues a message in a community public forum discussion, "a finishing team goes to 25 18 floors for finishing at nine am tomorrow, and enters the finishing team in the next week". After the community message is published, text extraction and behavior hypothesis mapping are carried out until next-day personnel enter to carry out behavior detection and fusion of public forum data and detect that the behavior does not belong to abnormal behavior, but supervision and management are required to be carried out on the activity and the personnel.
If information is published in a community forum, a greening department of municipal engineering has a person to carry out vegetation maintenance, and the on-line data is fused with data in an abnormal behavior database, so that the behavior of the person can not be defined as abnormal behavior on the same day, and false alarm is avoided.
5. The dynamically updated abstract network space abnormal behavior characteristic library comprises the following steps:
with the passage of time and the occurrence of abnormal behaviors, the event perception and early warning mechanism faces new challenges whenever new abnormal behaviors occur, and therefore, timely and even real-time updating is very necessary for the feature library at the upper layer.
Taking a community as an example of entering a batch of workers with safety caps, before the construction, various facilities of the community may have no scenes where the facilities need to be replaced or maintained, so that the characteristics of the behaviors do not exist in an upper database, but the behaviors belong to abnormal behaviors relative to the ordinary life of the community, if the detection and early warning are carried out according to an original characteristic library, the behaviors of the kind are set to be abnormal behaviors by a community situation perception and early warning mechanism and are notified to the community edge, so that the community edge makes a correct and unprofful decision, and therefore the characteristics of the behaviors need to be extracted, firstly, the behaviors of the community are not single behaviors, and secondly, most of the workers are uniform in installation and are provided with the safety caps. The people do not suddenly enter private places such as residential buildings and residential areas, but frequently enter construction areas or vegetation areas, so that scene labeling is carried out on the areas, the character database is updated, the scene, namely geographic information, is updated, visiting time is stamped, namely the feature database is updated, accordingly, the abnormal behavior feature database is updated on the aspect of time and space dimensions, when the situation perception and early warning system meets the same situation next time, correct responses or warnings are given through existing experiences, if a group of people is not unified and tries to illegally enter the residential buildings, the events are subjected to feature extraction and are matched with the behavior feature database, alarm response is given, and the central terminal updates and correctly processes the situations.
On one hand, updating the feature library on the character event is needed, and on the other hand, dynamic updating of the abnormal behavior feature library is needed in space, that is, the environment where the abnormal behavior is located needs to be dynamically updated, for example, a place which is originally not used in the community is reconstructed into an activity place of the community, so that community personnel can perform physical activities and open the space to the outside, and therefore, the features of the area need to be updated synchronously in the feature library, a more accurate reference feature library is provided for the abnormal behavior appearing in the area, and more comprehensive guarantee is provided for a system to make correct feedback.
6. Early warning mechanism based on complex event definition and dynamic excitation:
one event in the complex event is a piece of data, and the complex event processing is divided into an atomic event and a complex event.
The atomic events are specific situations and conditions, one atomic event is an interesting event which happens instantaneously, and for an environment such as a community, one atomic event may be described as follows:
e＝(ID,DeviceId,location,start,end,[value list])
there are very many temperature sensors in a community sensor, so there may be the following events: the third temperature sensor in five floors of fifteen residential buildings displays the temperature at 9 am of 12 months and 15 days in 2019, and the event is defined as:
e ═ e (0001, TemSensor,15 layers 5, 2019.12.159:00,2019.12.159: 00, [ Tem: 15; Hum: 28% ])
The atomic events of the community have been described formally in such a form that they are transmitted to the complex event handling mechanism through the proprietary protocol of the sensor device (wireless, 3G, bluetooth, etc.).
Complex event definition, in the complex event processing technology, an atomic event covers all events that can be detected in a system related to complex event processing, and a complex event is composed of the atomic event of the system and other complex events of the system combined by using AND or not equal logic conjunction words. The expression form of the complex event can be the atomic event in the system or the combination of other complex events according to a certain rule. These rules may be temporal associations, spatial associations, dependencies, or causal relationships. The complex event may be defined in the following way:
(1) any atomic event t is an event
(2) If T is an event, then non-T is also an event
(3) If both T1 and T2 are events, then all combinations of the logical and temporal relationships of T1 and T2 are events, e.g., (E1^ E2, E1afterE2, E1include E2, E1< E2) are events
(4) Complex events: and D ═ T | T is an event, then the complex event C ═ f (T1, T2, T3 … … TN), where f is the event constructor for constructing the complex event, and the specific result value is the specific result obtained for different complex event rules.
For example, if there are fifty security personnel in the community, five of them are A, B, C, D and E security team leaders, respectively, and their times to patrol the patrol are 6 o 'clock, 6 o' clock 30, 7 o 'clock 30 and 8 o' clock, five atomic events are generated, atomic event A indicates that team A leader arrives at patrol, and atomic event B indicates that team B leader arrives at ordinary position … …, the logical value of these atomic events is set to 1, and the complex event may be the complete arrival or the non-arrival of such events in the period of 6 o 'clock to 8 o' clock. Complex events differ from atomic events, as an example, in that complex events are directed to actions that occur within a period of time. Aiming at the complex event, the system can check the attendance of community workers and can also dynamically early warn the geographical position without security check.
The definition and management based on the complex event are the basis of dynamic early warning, and the processing mechanism of the complex event is very important.
7. The multi-level data processing and computing system based on the edge computing technology comprises the following steps:
due to the abundance of sensors and the arrival of the internet of things era of all things interconnection, the number of sensors in places such as communities is increased, data generated by edge equipment is rapidly increased, higher data transmission bandwidth and requirements are brought, meanwhile, the security situation perception model also puts higher real-time requirements on data processing, the traditional cloud computing model cannot effectively solve the dilemma, and at this time, a multi-level data processing and computing system based on the edge computing technology is needed.
Firstly, a large amount of temporary data generated by a community multi-source sensor are not completely uploaded to a cloud, the efficiency of the cloud is not reduced by means of the strong processing capacity of the cloud, the data are processed in time by a processor close to a data source in a 'local correction method', and the power consumption pressure of a network bandwidth and a data center can be greatly reduced. Meanwhile, a data producer is close to data processing, a cloud computing request is not needed, and delay of the whole system is greatly reduced, so that instantaneity required by the community security situation perception system is improved laterally. Moreover, the data source is a mass sensor of the community, but real data manufacturers are community human beings and behaviors, data needs to be processed on site by utilizing edge calculation instead of uploading user privacy, so that unnecessary sharing of the data is reduced, and the safety and the privacy of the data manufacturers are guaranteed to a certain extent. In the data processing layer at this level, facing edge devices (sensors), due to the dynamics of requesters of computing services, edge computing itself should have the characteristics of service discovery, and the rapid increase of the number of edge devices and the generation of a large amount of data place new requirements on rapid configuration and load balancing of edge computing. In this step, the massive data generated by the community edge device is primarily processed by utilizing the advantages of edge computing.
For example, in a community sensor, camera equipment, a temperature sensor, and a smoke alarm device perform relevant processing near a source through their own unique transmission protocols, such as data cleaning, data feature extraction, and the like on data generated by the camera equipment, data distribution and analysis of data generated by the temperature sensor over a period of time, and the like.
8. A high-throughput data processing and high-performance real-time computing engine is adopted in a central analysis platform:
after the data are transmitted to the center or the cloud, what needs to be done is to process a large amount of data in parallel, and one of the characteristics of the situation awareness and early warning mechanism is that high real-time performance is needed. Therefore, a high-throughput data processing platform and a high-performance real-time computing engine are necessarily constructed.
With the increase of data and users, the offline computing efficiency is lower and lower, the community users should enjoy real-time observation and detection, and the computing engine needs to collect, accommodate and store data in real time. The central processing unit is used for analyzing the acquired, received and stored data in real time to achieve the function of real-time reporting of clients, monitoring and analyzing the system and the users in real time, and monitoring and discovering dangerous behaviors in real time, namely, an early warning mechanism is really achieved.
And then, the data or the characteristics are transmitted to a cloud end, and the data is further processed and analyzed by using a high-performance processor, a high-fidelity algorithm and a high-response platform of the cloud end, so that a real-time situation perception and early warning system is really realized.
The present invention relates to the following related arts:
1. the space-time big data management and analysis technology comprises the following steps:
the time-space data has time and space dimensionality data, contains time, space and thematic three-dimensional information, and has the comprehensive characteristics of multiple sources, mass and quick updating. Due to the characteristics, the space-time data presents the complexity except for multi-dimensional, semantic and space-time dynamic association, so that a formalized expression association relation dynamic modeling and multi-scale association analysis method of space-time data multi-dimensional association description is needed, and quick and accurate task-oriented association constraint is provided by space-time big data collaborative calculation and reconstruction. The management and analysis technology of the space-time big data mainly comprises space-time data index and space-time big data information mining and analysis technology.
The spatio-temporal data indexing technology is a spatio-temporal data acquisition method, and most of researches mainly start from the following aspects: 1, efficient storage and acquisition of historical data, for the research on the aspect, a space-time index technology based on an R tree or a quadtree is mainly used at present, so that the resume index is used for reducing the space occupied by the index and improving the query efficiency; 2 for future state queries, the currently owned approach is the TPR tree and its modified version to support future predicted queries. The query of the spatio-temporal data refers to retrieving information such as a position state of an object at a certain time or time period in the past, present or future. Efficient space-time query is very important for a space-time database to come, and common space-time query methods include point query, window query, nearest neighbor query and the like.
With the arrival of the era of artificial intelligence, data explosion-type growth has also become a central importance for the analysis of space-time big data, and aiming at the characteristics of the space-time big data, the analysis method of the space-time big data is mainly divided into the methods of traditional machine learning, deep learning, data mining and the like. The good analysis method has the advantages that firstly, good data description is provided, including comprehensive expression and semantic expression of data shape forms, secondly, diagnosis and analysis are needed to be carried out on the data, deep mining is carried out on the data, internal relation and relevant logic of the data are searched, on the basis, predictive analysis is carried out on the data, deep and thorough understanding is carried out on the data in a time dimension, namely, the predictive analysis is carried out in the future, and finally, a solution is obtained on the basis of the analysis report.
2. Dynamic behavior analysis technique:
dynamic behavior analysis is opposite to static behavior analysis, wherein static behavior analysis is used for analyzing and verifying a result to find reasons and methods, and dynamic behavior analysis is mainly used for analyzing a process to find reasons. Briefly, while dynamic behavior analysis also requires comprehensiveness, it focuses on what the analysis is why these are not the same as static analysis, which focuses on how the analysis does.
Static behavior analysis generally uses tools with very strong hierarchical logicality, such as a mind map (tree diagram, logic diagram) and the like, and dynamic behavior analysis mainly uses a flow chart, because the flow chart records each link in detail, analysis is performed according to each link, and the requirements of dynamic behavior analysis, namely an analysis process, are completely met. The analysis aim of dynamic analysis, namely the analysis process, is to optimize each flow and improve the efficiency of each step so as to carry out overall speed increase.
The main tool of the dynamic behavior analysis technique selects the flow chart because the flow chart can better plan the flow, describe the flow and optimize the flow. And a mature thinking model is used for ensuring the comprehensive, effective and usable analysis result.
3. The human-computer interface technology of the Internet of things comprises the following steps:
the human-computer interface technology is used for achieving information and processing interaction between a person and a sensor terminal, the human-computer interface is an interface of input/output equipment for establishing contact between the person and a computer and exchanging information, in the field of internet of things, the information is a series of data generated by a multi-source heterogeneous sensor, and the equipment comprises a keyboard, a display, a printer, a mouse and the like. The man-machine interface of the internet of things is a device circuit for realizing information transmission between a computer and man-machine interaction equipment. The human-computer interaction device and the human-computer interaction device complete two tasks, namely information form conversion and information transmission control, and a parallel communication mode is adopted in information transmission between the human-computer interaction device and a human-computer interface.
4. Edge calculation techniques:
the edge computing refers to an open platform which is close to one side of an object or a data source and integrates network, computing, storage and application core capabilities. The network edge side can be any functional entity from a data source to the cloud computing center, and the entities carry an edge computing platform with the core capabilities of network fusion, computing, storage and application, so that real-time, dynamic and only service computing is provided for end users. Unlike processing and algorithm decision making in a cloud, edge computing pushes intelligence and computation to a behavior closer to reality, and is mainly reflected in aspects of multi-source data heterogeneous processing, bandwidth load and resource waste, resource limitation, safety, privacy protection and the like.
5. High performance computing techniques:
high performance computing refers to computing systems and environments that typically use many processors (as part of a single machine) or several computers organized in a cluster (operating as a single computing resource). The application programs running on several circles with high performance generally use a parallel algorithm, a large common problem is divided into a plurality of small subproblems according to a certain rule, calculation is carried out on different nodes in a cluster, and the processing results of the small problems can be combined into the final result of the original problem after processing. Since the computation of these small problems can generally be done in parallel, the processing time of the problems can be shortened. In the calculation process of the high-performance cluster, all nodes work cooperatively, the nodes process part of a large problem respectively and exchange data according to needs in the process, and the processing result of each node is part of the final result. The processing power of a high performance cluster is proportional to the size of the cluster, which is the sum of the processing power of each node in the cluster, but such a cluster generally has no high availability. There are many classification methods for high performance computing. High performance computations are classified here from the perspective of relationships between parallel tasks.
There is a class of high performance computing that can be divided into several sub-tasks that can be in parallel, and the sub-tasks have no relationship to each other. Because one common feature of this type of application is searching for certain specific patterns over large amounts of data, this type of computation is referred to as high-throughput computation.
Another class of computations, just as opposed to high-throughput computations, can be divided into several parallel subtasks, but the relationship between the subtasks is very tight, requiring a large amount of data to be exchanged. This category is distributed computing. Distributed high performance computing falls into the category of multiple instruction streams-multiple data streams.
The community security situation perception and early warning method has the beneficial effects that: according to the technical scheme, the current community data detected by the multi-source heterogeneous sensor is acquired; inputting the current community data into a pre-established behavior detection model based on dynamic network time-space, performing data feature fusion, and extracting behavior feature data; sending the behavior characteristic data to a central analysis platform for processing and analysis; and carrying out community security situation perception and early warning according to the processing and analyzing results fed back by the central analysis platform, realizing real-time situation perception and early warning, and avoiding false alarm in community activities.
In order to achieve the above object, the present invention further provides a community security situation awareness and early warning system, where the system includes a memory, a processor, and a community security situation awareness and early warning program stored on the processor, and the steps of the method according to the above embodiment are executed when the community security situation awareness and early warning program is called by the processor, which is not described herein again.
In order to achieve the above object, the present invention further provides a computer-readable storage medium, where a community security situation awareness and early warning program is stored on the computer-readable storage medium, and the steps of the method according to the above embodiment are executed when the community security situation awareness and early warning program is called by a processor, which is not described herein again.
The above description is only for the preferred embodiment of the present invention and is not intended to limit the scope of the present invention, and all equivalent structures or flow transformations made by the present specification and drawings, or applied directly or indirectly to other related arts, are included in the scope of the present invention.
Claims (10)
1. A community security situation awareness and early warning method is characterized by comprising the following steps:
acquiring current community data detected by a multi-source heterogeneous sensor;
inputting the current community data into a pre-established behavior detection model based on dynamic network time-space, performing data feature fusion, and extracting behavior feature data;
sending the behavior characteristic data to a central analysis platform for processing and analysis;
and sensing and early warning the community security situation according to the processing and analyzing results fed back by the central analysis platform.
2. The community security situation awareness and early warning method of claim 1, wherein the step of sending the behavior feature data to a central analysis platform for processing and analysis comprises:
and sending the behavior characteristic data to a central analysis platform, and processing and analyzing the behavior characteristic data by the central analysis platform by adopting a high-pass data processing and high-performance real-time computing engine.
3. The community security situation awareness and early warning method according to claim 1, wherein the step of inputting the current community data into a pre-established behavior detection model based on dynamic network spatio-temporal to perform data feature fusion and extracting behavior feature data comprises:
and inputting the current community data into a pre-established behavior detection model based on dynamic network space-time to perform data feature fusion, and extracting behavior feature data by adopting a principal component analysis method, a linear discriminant analysis method, a multidimensional scale analysis method, an analysis method based on flow learning, an independent component analysis method or a kernel principal component analysis method.
4. The community security situation awareness and early warning method according to claim 1, wherein the step of obtaining current community data detected by the multi-source heterogeneous sensor further comprises:
processing the current community data by adopting a multilayer and data processing and computing system based on an edge computing technology to obtain processed community data;
the step of inputting the current community data into a pre-established dynamic network spatio-temporal based behavior detection model comprises the following steps:
and inputting the processed community data into a pre-established behavior detection model based on dynamic network space-time.
5. The community security situation awareness and pre-warning method according to any one of claims 1 to 4,
the step of obtaining the current community data detected by the multi-source heterogeneous sensor comprises the following steps:
the method comprises the steps of pre-establishing a dynamic network space-time based behavior detection model, wherein the dynamic network space-time based behavior detection model is an abstract data model which is established aiming at a network space and takes continuous behaviors as objects;
the step of establishing a dynamic network spatiotemporal behavior detection model comprises the following steps:
based on interesting continuous behaviors, a time-space feature structure capable of fusing multi-source heterogeneous sensor data is established, and meanwhile, adjustable weights of different time-space feature dimensions are determined according to the obvious feature dimensions of specific access data.
6. The community security situation awareness and early warning method according to claim 5, wherein the step of pre-establishing a dynamic network spatiotemporal-based behavior detection model comprises:
and pre-establishing a network space-time characteristic model based on continuous behaviors.
7. The community security situation awareness and early warning method according to claim 5, wherein the step of pre-establishing a dynamic network spatiotemporal-based behavior detection model further comprises:
and pre-establishing a network space environment characteristic model based on online and offline fusion data.
8. The community security situation awareness and early warning method according to claim 5, wherein the step of pre-establishing a dynamic network spatiotemporal-based behavior detection model further comprises:
and (4) establishing an abstract network space abnormal behavior characteristic library based on dynamic update in advance.
9. A community security posture awareness and pre-warning system, the system comprising a memory, a processor, and a community security posture awareness and pre-warning program stored on the processor, the community security posture awareness and pre-warning program when invoked by the processor performing the steps of the method of any of claims 1-8.
10. A computer-readable storage medium having stored thereon a community security posture awareness and early warning program, which when invoked by a processor performs the steps of the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010047997.1A CN111260525A (en) | 2020-01-16 | 2020-01-16 | Community security situation perception and early warning method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010047997.1A CN111260525A (en) | 2020-01-16 | 2020-01-16 | Community security situation perception and early warning method, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111260525A true CN111260525A (en) | 2020-06-09 |
Family
ID=70950624
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010047997.1A Pending CN111260525A (en) | 2020-01-16 | 2020-01-16 | Community security situation perception and early warning method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111260525A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783084A (en) * | 2020-06-29 | 2020-10-16 | 济南浪潮高新科技投资发展有限公司 | Security situation sensing method, device and medium |
| CN112087731A (en) * | 2020-09-11 | 2020-12-15 | 山东润一智能科技有限公司 | Edge processing host, system and method for information acquisition, processing and transmission of Internet of things |
| CN113094503A (en) * | 2021-03-23 | 2021-07-09 | 重庆特斯联智慧科技股份有限公司 | Community security monitoring method and system based on multidimensional data clustering |
| CN113329205A (en) * | 2021-04-09 | 2021-08-31 | 成都中科创达软件有限公司 | Internet of things video data processing system, intelligent retail system, method and device |
| CN113609445A (en) * | 2021-08-03 | 2021-11-05 | 中冀建勘集团有限公司 | Multi-source heterogeneous monitoring data processing method, terminal device and readable storage medium |
| CN115021996A (en) * | 2022-05-26 | 2022-09-06 | 云盾智慧安全科技有限公司 | Situation awareness and dynamic reconstruction method and device for cloud security center and storage medium |
| CN115277249A (en) * | 2022-09-22 | 2022-11-01 | 山东省计算中心（国家超级计算济南中心） | Network security situation perception method based on cooperation of multi-layer heterogeneous network |
| CN115904499A (en) * | 2023-02-27 | 2023-04-04 | 珠海市鸿瑞信息技术股份有限公司 | Artificial intelligence-based dangerous situation perception real-time early warning system and method |
| CN116680752A (en) * | 2023-05-23 | 2023-09-01 | 杭州水立科技有限公司 | Hydraulic engineering safety monitoring method and system based on data processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007052248A1 (en) * | 2005-11-03 | 2007-05-10 | Elta Systems Ltd. | Vocal alert unit having automatic situation awareness of moving mobile nodes |
| CN102790981A (en) * | 2012-06-29 | 2012-11-21 | 石化盈科信息技术有限责任公司 | Real-time warning method under space-time dynamic mode of sensor network |
| CN109241223A (en) * | 2018-08-23 | 2019-01-18 | 中国电子科技集团公司电子科学研究院 | The recognition methods of behavior whereabouts and platform |
| CN109656793A (en) * | 2018-11-22 | 2019-04-19 | 安徽继远软件有限公司 | A kind of information system performance stereoscopic monitoring method based on multi-source heterogeneous data fusion |
| CN110459027A (en) * | 2019-08-15 | 2019-11-15 | 青岛文达通科技股份有限公司 | A kind of Community Safety means of defence and system based on multi-source heterogeneous data fusion |
-
2020
- 2020-01-16 CN CN202010047997.1A patent/CN111260525A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007052248A1 (en) * | 2005-11-03 | 2007-05-10 | Elta Systems Ltd. | Vocal alert unit having automatic situation awareness of moving mobile nodes |
| CN102790981A (en) * | 2012-06-29 | 2012-11-21 | 石化盈科信息技术有限责任公司 | Real-time warning method under space-time dynamic mode of sensor network |
| CN109241223A (en) * | 2018-08-23 | 2019-01-18 | 中国电子科技集团公司电子科学研究院 | The recognition methods of behavior whereabouts and platform |
| CN109656793A (en) * | 2018-11-22 | 2019-04-19 | 安徽继远软件有限公司 | A kind of information system performance stereoscopic monitoring method based on multi-source heterogeneous data fusion |
| CN110459027A (en) * | 2019-08-15 | 2019-11-15 | 青岛文达通科技股份有限公司 | A kind of Community Safety means of defence and system based on multi-source heterogeneous data fusion |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111783084A (en) * | 2020-06-29 | 2020-10-16 | 济南浪潮高新科技投资发展有限公司 | Security situation sensing method, device and medium |
| CN112087731A (en) * | 2020-09-11 | 2020-12-15 | 山东润一智能科技有限公司 | Edge processing host, system and method for information acquisition, processing and transmission of Internet of things |
| CN112087731B (en) * | 2020-09-11 | 2023-05-23 | 山东润一智能科技有限公司 | Edge processing host, system and method for information acquisition, processing and transmission of Internet of things |
| CN113094503A (en) * | 2021-03-23 | 2021-07-09 | 重庆特斯联智慧科技股份有限公司 | Community security monitoring method and system based on multidimensional data clustering |
| CN113329205B (en) * | 2021-04-09 | 2023-05-05 | 成都中科创达软件有限公司 | Internet of things video data processing system, method and device |
| CN113329205A (en) * | 2021-04-09 | 2021-08-31 | 成都中科创达软件有限公司 | Internet of things video data processing system, intelligent retail system, method and device |
| CN113609445A (en) * | 2021-08-03 | 2021-11-05 | 中冀建勘集团有限公司 | Multi-source heterogeneous monitoring data processing method, terminal device and readable storage medium |
| CN115021996A (en) * | 2022-05-26 | 2022-09-06 | 云盾智慧安全科技有限公司 | Situation awareness and dynamic reconstruction method and device for cloud security center and storage medium |
| CN115021996B (en) * | 2022-05-26 | 2023-11-21 | 云盾智慧安全科技有限公司 | Situation awareness and dynamic reconstruction method and device of cloud security center and storage medium |
| CN115277249A (en) * | 2022-09-22 | 2022-11-01 | 山东省计算中心（国家超级计算济南中心） | Network security situation perception method based on cooperation of multi-layer heterogeneous network |
| CN115277249B (en) * | 2022-09-22 | 2022-12-20 | 山东省计算中心（国家超级计算济南中心） | Network security situation perception method based on cooperation of multi-layer heterogeneous network |
| CN115904499A (en) * | 2023-02-27 | 2023-04-04 | 珠海市鸿瑞信息技术股份有限公司 | Artificial intelligence-based dangerous situation perception real-time early warning system and method |
| CN116680752A (en) * | 2023-05-23 | 2023-09-01 | 杭州水立科技有限公司 | Hydraulic engineering safety monitoring method and system based on data processing |
| CN116680752B (en) * | 2023-05-23 | 2024-03-19 | 杭州水立科技有限公司 | Hydraulic engineering safety monitoring method and system based on data processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111260525A (en) | Community security situation perception and early warning method, system and storage medium | |
| Hamdi et al. | Spatiotemporal data mining: a survey on challenges and open problems | |
| Siow et al. | Analytics for the internet of things: A survey | |
| US11900396B2 (en) | Systems and methods for generating a relationship among a plurality of datasets to generate a desired attribute value | |
| Stolpe | The internet of things: Opportunities and challenges for distributed data analysis | |
| L’heureux et al. | Machine learning with big data: Challenges and approaches | |
| Alahakoon et al. | Self-building artificial intelligence and machine learning to empower big data analytics in smart cities | |
| Huang et al. | A cloud-enabled automatic disaster analysis system of multi-sourced data streams: An example synthesizing social media, remote sensing and Wikipedia data | |
| Deshpande et al. | Using Probabilistic Models for Data Management in Acquisitional Environments. | |
| Tsai et al. | Future internet of things: open issues and challenges | |
| CN110663030A (en) | Edge device, system and method for processing extreme data | |
| Nayak et al. | A review on edge analytics: Issues, challenges, opportunities, promises, future directions, and applications | |
| CN116881744A (en) | Operation and maintenance data distribution method, device, equipment and medium based on Internet of things | |
| Yin et al. | A novel temporal and spatial panorama stream processing engine on IoT applications | |
| Curry et al. | Multimodal event processing: A neural-symbolic paradigm for the internet of multimedia things | |
| Wang et al. | Concept drift-based runtime reliability anomaly detection for edge services adaptation | |
| Raj et al. | The internet of things and big data analytics: integrated platforms and industry use cases | |
| Aved | Scene understanding for real time processing of queries over big data streaming video | |
| Bhargavi et al. | Semantic intrusion detection with multisensor data fusion using complex event processing | |
| Gubareva et al. | Literature Review on the Smart City Resources Analysis with Big Data Methodologies | |
| CN114780864B (en) | Human-object-space interaction model construction method based on knowledge graph | |
| Zheng et al. | Towards edge-cloud collaborative machine learning: A quality-aware task partition framework | |
| Mantzaris et al. | Adaptive network diagram constructions for representing big data event streams on monitoring dashboards | |
| Hiriyannaiah et al. | Data Reduction Techniques in Fog Data Analytics for IoT Applications | |
| Lazrak et al. | Enabling distributed intelligence in Internet of Things: an air quality monitoring use case |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200609 |